download a site using wget

wget_site.sh

#!/bin/bash
function wget_site(){
	## Remove protocol part of domain to add it to the allow list
	# source : https://www.cyberciti.biz/faq/get-extract-domain-name-from-url-in-linux-unix-bash/
	local url="$1"
	local domain="$1"
	domain="${domain#http://}"
	domain="${domain#https://}"
	domain="${domain#ftp://}"
	domain="${domain#scp://}"
	domain="${domain#scp://}"
	domain="${domain#sftp://}"
	## Remove username and/or username:password part of domain
	domain="${domain#*:*@}"
	domain="${domain#*@}"
	## Remove rest of domains
	domain=${domain%%/*}

	# --no-clobber, -nc      : refuse to download newer copies of downloaded files
	# --adjust-extension, -E : Appends .html
	# --span-hosts, -H       : retrieve across hosts
	# --convert-links, -k    : create a self-contained dir of all of its external dependencies
	# --backup-converted, -K : stash a copy of the original HTML
	# --page-requisites, -p  : download all the files that are necessary
	# --tries=number, -t     : number of tries
	# --timeout=seconds, -T  : set dns, connect and read to the same timeout
	# --limit-rate           : Limit the download speed
	# --no-parent, -np       : never leave the existing hierarchy
	# --max-redirect         : maximum redirections allowed per page.
	# --domains, -D          : comma-separated list of accepted domains.
	# --level, -l            : Specify recursion maximum depth. default 5

	local wget_args=('-nc' '-E' '-H' '-k' '-K' '-r' '-p' '-t' '1' '-T' '5' '--limit-rate=400k' '-np' '--max-redirect' '1')
  
	## download only from the main domain.
	local wget_allow=('--domains' ${domain})


	wget "${wget_args[@]}" "${wget_allow[@]}" "${url}"
}